Real-Time Path-Guiding Based on Parametric Mixture Models
Loading...
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Path-Guiding algorithms for sampling scattering directions can drastically decrease the variance of Monte Carlo estimators of Light Transport Equation, but their production usage was limited to offline rendering because of memory and computational limitations. We introduce a new robust screen-space technique that is based on online learning of parametric mixture models for guiding the real-time path-tracing algorithm. It requires storing of 8 parameters for every pixel, achieves a reduction of FLIP metric up to 4 times with 1 spp rendering. Also, it consumes less than 1.5ms on RTX 2070 for 1080p and reduces path-tracing timings by generating more coherent rays by about 5% on average. Moreover, it leads to significant bias reduction and a lower level of flickering of SVGF output.
Description
CCS Concepts: Computing methodologies --> Ray tracing
@inproceedings{10.2312:egs.20221024,
booktitle = {Eurographics 2022 - Short Papers},
editor = {Pelechano, Nuria and Vanderhaeghe, David},
title = {{Real-Time Path-Guiding Based on Parametric Mixture Models}},
author = {Derevyannykh, Mikhail},
year = {2022},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {978-3-03868-169-4},
DOI = {10.2312/egs.20221024}
}